- Atlas
- Computer Science
- Congestion Control
Congestion Control
Congestion control is the set of rules by which senders and the network decide how much data may be in flight at once.
9 frameworks, from 1988 to today · Networks · Computer Science
- Additive increase/multiplicative decrease 1988-Present
- Active queue management 1993-Present
- Delay-based congestion control 1994-Present
- Explicit congestion signaling 1994-Present
- Datagram and real-time media congestion control 1996-Present
- Wireless and lossy-link congestion control 1997-Present
- Explicit Rate-Based Congestion Control 2002-Present
- Low-latency data-center congestion control 2010-Present
- Model-based bandwidth and delay estimation 2016-Present
Overview
Congestion control is the set of rules by which senders and the network decide how much data may be in flight at once1. When many computers share a link, a switch, or a radio channel, demand can exceed capacity1. Packets then queue, delay rises, and buffers overflow1. Congestion control is what keeps that from collapsing into a state where everyone sends as fast as possible and almost nothing gets through1. It is one of the load-bearing ideas of the Internet: the network itself is deliberately simple, and most of the intelligence that keeps it stable sits in the endpoints. The history of the field is the history of how that endpoint intelligence was invented, refined, and repeatedly rethought as the network changed around it.
The collapse of the early Internet and the first fix
In the mid-1980s the Internet suffered a series of "congestion collapses." Throughput on some paths fell by orders of magnitude while hosts kept retransmitting1. The cause was that the early Transmission Control Protocol (TCP) had no notion of how much the network could absorb. A sender pushed data until a packet was lost, then retransmitted, and the retransmissions themselves added load, making loss more likely1. The network had no feedback loop to tell senders to slow down.
The fix came from Van Jacobson, whose 1988 paper with Michael Karels described the algorithms that became TCP's congestion control. The central idea was the congestion window: a limit, maintained by the sender, on how many unacknowledged bytes may be outstanding2. The sender grows the window when acknowledgments arrive and shrinks it when packets are lost2. Jacobson's scheme had two phases. Slow start begins with a small window and doubles it each round trip, so a connection ramps up quickly from nothing. Congestion avoidance then grows the window by roughly one packet per round trip, a cautious probing of spare capacity. On loss, the sender cuts the window, classically in half2.
This is additive increase, multiplicative decrease (AIMD)3. The name describes the shape of the control: the window climbs linearly while things go well and drops sharply when they don't. The reason it works is a property of how competing senders share a bottleneck. If several AIMD flows share one link, their windows converge toward a fair split, because a flow that is getting more than its share loses more when congestion hits3. The scheme is loss-based: it treats a dropped packet as the signal that the network is full. Jacobson also added fast retransmit and fast recovery, so a sender could react to a few duplicate acknowledgments without waiting for a timeout. These algorithms, refined through the late 1980s and standardized in the early 1990s, are the foundation on which nearly everything since builds.
The router's role: active queue management
Loss-based control has a weakness. If a router's buffer is large, it fills completely before any packet is dropped, so every sender learns about congestion only after long queues have built up4. The delay is felt by everyone sharing the link. The alternative was to have routers signal congestion earlier, before buffers overflow.
The first widely discussed proposal was the DECbit scheme from the late 1980s, in which routers set a congestion bit in packets when average queue length crossed a threshold. The idea reached the Internet community through Random Early Detection (RED), published by Sally Floyd and Van Jacobson in 1993. RED routers monitor the average queue length and, as it rises toward a maximum threshold, drop arriving packets with a probability that increases with the queue1. The randomness matters: it spreads the signal across many flows so that they back off together rather than in lockstep. This family of techniques is called active queue management (AQM): the router manages its queue actively rather than letting it fill and overflow passively15.
RED was influential but hard to tune, and deployment was limited. Its descendants and rivals—among them variations that drop based on the queue's instantaneous length or that target a fixed delay—kept the idea alive. AQM matters because it moves part of the congestion signal from the endpoint's inference ("a packet was lost, so somewhere is full") to the network's explicit or statistical hint. That shift becomes central to later developments.
Explicit signals and rate-based control
A separate line of work asked whether the network could tell senders directly what rate to use, rather than making them infer it from loss. Explicit Congestion Notification (ECN), specified in the late 1990s and early 2000s, lets a router mark a packet instead of dropping it, and the receiver echoes the mark back so the sender slows down without any loss6. ECN is a modest change but it removes the ambiguity between congestion loss and other kinds of loss.
More ambitious was explicit rate-based control, in which routers compute and communicate a sending rate. The Available Bit Rate (ABR) service in ATM networks, developed in the 1990s, had switches feed back explicit rates to sources. In the Internet, the Rate Control Protocol (RCP) proposed that routers calculate a fair rate for each flow and stamp it into packets, so senders need not probe at all. These designs promised fast convergence and low queues, but they required routers to keep per-flow state, which conflicted with the Internet's preference for stateless, simple forwarding. They remained largely research proposals, though their ideas about explicit feedback resurface in modern data-center designs.
When loss stops meaning congestion
By the late 1990s, wireless links exposed a flaw in loss-based control. On a radio link, packets are lost to interference, fading, and handoffs, not because the network is congested. A TCP sender cannot tell the difference, so it halves its window on every such loss and performs badly. The field's response took several forms.
One approach was to hide wireless loss from the sender: split the connection at the wireless edge, or add link-layer retransmissions so the radio's losses are repaired locally. Another was to make the sender smarter. TCP Westwood, from the early 2000s, estimated the bottleneck bandwidth from the rate of returning acknowledgments and set the window from that estimate after a loss, rather than blindly halving. A third line used delay as the congestion signal instead of loss. If a sender watches the round-trip time, rising delay indicates that queues are building—congestion—while a lost packet on a lossy link may say nothing about congestion. Delay-based control had been explored as early as the 1980s, and it returned in schemes such as TCP Vegas (mid-1990s), which compared the measured and expected round-trip times to keep queues small. Vegas was fair and gentle but lost out in competition with loss-based flows, which grab more bandwidth when sharing a link. This fairness problem—delay-based flows being crowded out by aggressive loss-based ones—became a recurring theme.
Model-based estimation
A more systematic answer to "what is the network's capacity?" came from model-based bandwidth and delay estimation. Instead of reacting to individual loss events, a sender builds a model of the path and uses it to set its rate. The best-known example is TCP BBR, published by Neal Cardwell and colleagues in 2016. BBR periodically measures the bottleneck bandwidth (from the rate at which acknowledgments return) and the minimum round-trip time (the path's propagation delay with empty queues). It then sends at a rate matched to that model, probing upward occasionally to check whether more capacity has appeared. Because it does not treat loss as the primary congestion signal, BBR performs well on lossy links and keeps queues short on many paths. It also raised new questions: BBR flows can be unfair to loss-based flows sharing a bottleneck, and its behavior in the presence of deep buffers and competing traffic is still studied.
Congestion control beyond TCP
TCP was never the only transport. The User Datagram Protocol (UDP) carries no congestion control at all, and applications built on it—streaming media, voice, games—had to add their own or risk starving the network. The Datagram Congestion Control Protocol (DCCP), standardized in the mid-2000s, offered a framework for congestion-controlled datagram traffic, with pluggable algorithms. Meanwhile, the rise of real-time media drove work on rate-based control for video and voice, where the goal is a smooth sending rate rather than a window that jumps. The Real-time Transport Protocol (RTP) and its control protocol carried feedback that let senders adapt. These efforts established that congestion control is a general problem for any sender, not a TCP-specific one, and that different applications want different trade-offs between smoothness, latency, and fairness.
The data center rewrites the rules
The 2010s brought a setting where the old assumptions broke down: the data center. Here the network is owned by one operator, round-trip times are microseconds, links are fast, and switches have shallow buffers. Loss-based TCP reacts too slowly and its timeouts are far too coarse. The result was a burst of new designs.
Data Center TCP (DCTCP), from Mohammad Alizadeh and colleagues in 2010, used ECN marks to let senders react to the fraction of marked packets, keeping queues very short. Priority Flow Control and lossless fabrics addressed buffer overflow at the link layer. A wave of schemes followed—TIMELY used round-trip-time gradients; DCQCN brought congestion control to remote direct memory access (RDMA) traffic; Swift combined delay and loss signals. The common thread is low-latency congestion control: the goal is not just high throughput but keeping queues near empty, because in a data center a millisecond of queuing is a large fraction of the total delay. These designs also leaned on programmable switches and software-defined networking, which made it practical to give the network a more active role in signaling.
Where the field stands
Today congestion control is a family of approaches rather than a single algorithm. Loss-based AIMD remains the baseline, embedded in TCP and in the congestion control of QUIC, the transport that now carries much web traffic. Delay-based and model-based schemes (Vegas descendants, BBR) compete with it, and hybrid designs blend loss, delay, and explicit signals. AQM is enjoying a revival, with algorithms designed to keep queuing delay low for latency-sensitive traffic. Data-center and low-latency designs have pushed the field toward explicit feedback and fine-grained control, while wireless and satellite networks keep the lossy-link problem alive.
The open questions are old ones in new clothes. How should flows that use different signals share a link fairly? How should congestion control behave when the path crosses technologies with wildly different characteristics? Can machine learning set rates better than hand-designed rules, and can such controllers be trusted? And as the network becomes more programmable, how much of the control should move from the endpoint into the network itself? The answers will be written by the same kind of reasoning that produced the congestion window: measure what the network is doing, model it, and adjust.
References
- Network congestion (Congestion control, Network capacity, introduction, Congestive collapse, Random early detection, Active queue management), Wikipedia
- TCP congestion control (Congestion window, TCP Tahoe and Reno), Wikipedia
- Additive increase/multiplicative decrease, Wikipedia
- Random early detection, Wikipedia
- Active queue management, Wikipedia
- Explicit Congestion Notification, Wikipedia
The frameworks of Congestion Control
Each framework is a way of working the field has used: when it held, and the question it answers.
- 1988-Present
Additive increase/multiplicative decrease
How should senders adjust their rate to share a network fairly?
- 1993-Present
Active queue management
When should routers signal congestion before buffers overflow?
- 1994-Present
Delay-based congestion control
Can rising delay tell a sender the network is congested?
About Delay-based congestion control
In the 1990s, as the Internet grew beyond its research origins, congestion control faced a fundamental question: could a sender detect incipient congestion before packets were actually dropped? Delay-Based Congestion Control offered a distinctive answer. Instead of waiting for the blunt signal of packet loss, this framework proposed that a sender should monitor changes in round-trip time (RTT)—the time a packet takes to travel to the receiver and back. Rising delays, the argument went, reveal growing queue occupancy inside routers, giving an early warning that the path is becoming congested. This made delay a gentler, more proactive signal than loss, and it opened up a new design space for transport protocols that could react before buffers overflowed.Delay-Based Congestion Control is a member of the End-to-End family—it keeps the network core simple and places all intelligence at the endpoints—but it diverges sharply from the dominant AIMD/TCP paradigm. Where AIMD/TCP treats the network as a black box that only reveals congestion through dropped packets, delay-based schemes treat the network as a transparent pipe whose internal state can be inferred from timing. The core curriculum for this framework centers on a handful of concepts that define how delay is measured, interpreted, and turned into a control signal.Core Curriculum- Round-Trip Time (RTT): The fundamental observable. The sender measures the time between sending a packet and receiving its acknowledgment. This is the raw material from which congestion signals are extracted.
- Base RTT: The minimum observed RTT when the path is unloaded. It serves as a reference point: any increase above base RTT is attributed to queuing delay in routers.
- Queuing Delay: The component of RTT that varies with congestion. It is the difference between current RTT and base RTT, representing time spent waiting in router buffers.
- Self-Clocking: The insight that acknowledgments returning from the receiver act as a natural clock for the sender. Each ACK signals that a packet has been delivered, allowing the sender to pace new transmissions without needing an external timer.
- Window-Based Control: The sender limits how many packets it can have in flight at once, expressed as a congestion window. Delay-based schemes adjust this window in response to RTT changes.
- Rate-Based Control: An alternative to window-based control where the sender regulates its transmission rate (packets per second) directly. Some delay-based protocols use rate rather than window to match the observed path capacity.
- Additive Increase / Multiplicative Decrease (AIMD): The classic rule borrowed from TCP: gradually increase the window when the path seems uncongested, and cut it sharply when congestion is detected. Delay-based frameworks adapt this rule to use delay thresholds rather than loss events.
- Delay Threshold: A predefined RTT increase (e.g., a doubling of base RTT) that triggers a multiplicative decrease. This replaces the loss-based trigger of AIMD/TCP.
- Queue Occupancy Estimation: The sender estimates how many packets are queued ahead of it by comparing current RTT to base RTT and factoring in the bottleneck link rate. This turns delay into a proxy for queue depth.
- Fairness: The property that multiple competing flows should converge to roughly equal bandwidth shares. Delay-based frameworks must ensure that their control rules do not let one flow starve others.
- Stability: The requirement that the sender's window or rate should not oscillate wildly. Delay-based schemes must avoid overreacting to transient RTT spikes.
- Burstiness: The tendency of a sender to transmit packets in clusters rather than a smooth stream. Delay-based control can reduce burstiness by pacing transmissions with ACK arrivals.
Intellectual HistoryDelay-Based Congestion Control emerged in the mid-1990s as a direct response to the limitations of AIMD/TCP. Van Jacobson's 1988 TCP congestion control algorithms had saved the Internet from congestion collapse, but they relied entirely on packet loss as a signal. Loss is a late indicator—it only appears after a buffer has already overflowed. Researchers began asking whether a sender could detect the buildup before the drop.The seminal work came from Raj Jain in 1994, who proposed a scheme called TCP Vegas. Jain showed that a sender could estimate the queue occupancy at the bottleneck router by comparing current RTT to the minimum observed RTT (base RTT). When the estimated queue grew beyond a threshold, the sender would reduce its window. Vegas was the first complete delay-based congestion control protocol, and it demonstrated that delay could serve as a reliable, early congestion signal. Its key insight—that queuing delay reveals incipient congestion—became the foundation of the entire framework.TCP Vegas was never widely deployed, but it inspired a line of research that continued through the late 1990s. TCP Reno (1996) incorporated some of Vegas's ideas, though it remained primarily loss-based. TCP NewReno (1998) improved loss recovery but did not adopt delay-based control. The framework's influence was more conceptual than practical during its dominance window: it established that delay was a viable signal, and it set the stage for later protocols that would combine delay with other indicators.Delay-Based Congestion Control coexisted with its peer frameworks throughout the 1990s. Router-Assisted schemes (DECbit, RED, ECN) asked routers to mark packets before dropping them, but they required router changes that were slow to deploy. Equation-Based Congestion Control (TFRC, 2000) would later model the path's behavior mathematically, using delay as one input among many. High-Speed Congestion Control (2002) addressed the problem of filling large pipes without loss, and it often used delay-based pacing. Hybrid frameworks (2005) combined loss, delay, and ECN signals. Model-Based Congestion Control (BBR, 2016) would eventually use delay to estimate the bottleneck bandwidth, but it did so through a model of the path rather than direct queuing delay.Delay-Based Congestion Control never replaced AIMD/TCP as the default paradigm, but it permanently changed the conversation. It showed that the network's internal state was readable from the endpoints, and it gave later frameworks a vocabulary for talking about queuing delay, base RTT, and self-clocking. Its legacy is not a single dominant protocol but a set of concepts that every congestion control designer must now understand.The 8 concepts its tower teaches
- Additive Increase / Multiplicative Decrease (AIMD)
- Base RTT
- Delay Threshold
- Queuing Delay
- Rate-Based Control
- Round-Trip Time (RTT)
- Self-Clocking
- Window-Based Control
- 1994-Present
Explicit congestion signaling
Should the network tell senders directly how fast to send?
- 1996-Present
Datagram and real-time media congestion control
How should real-time and datagram traffic control its sending rate?
- 1997-Present
- 2002-Present
Explicit Rate-Based Congestion Control
Can routers compute a fair rate for each flow?
- 2010-Present
Low-latency data-center congestion control
How can data-center traffic keep latency very low?
- 2016-Present
Model-based bandwidth and delay estimation
Can a sender model the path's capacity and delay?
How the ideas connect
Each arrow runs from an earlier idea to the later one it shaped. The list below says what passed between them.
Active queue management influenced by Additive increase/multiplicative decrease
Floyd and Jacobson's RED was designed as a router-side complement to the loss-based AIMD control they had helped establish: early drops let AIMD senders back off before buffers overflow. RED's probabilistic marking spreads the congestion signal across AIMD flows so they converge together.
Carried by Sally Floyd; Van Jacobson; Random Early Detection Gateways for Congestion Avoidance (1993).
Low-latency data-center congestion control influenced by Explicit congestion signaling
DCTCP used ECN marking at data-center switches, with senders reacting to the fraction of marked packets, to achieve low latency and high throughput. The explicit congestion signal that ECN introduced became the central mechanism of low-latency data-center control.
Carried by Mohammad Alizadeh; DCTCP (2010).
Delay-based congestion control reacted against Additive increase/multiplicative decrease
TCP Vegas was built as an alternative to the loss-based AIMD of Jacobson's TCP: it used measured versus expected round-trip time to detect incipient congestion and keep queues small instead of waiting for a drop. Its designers framed it explicitly against the loss-as-signal assumption.
Carried by Lawrence Brakmo; Larry Peterson; TCP Vegas (1994).
Explicit congestion signaling influenced by Additive increase/multiplicative decrease
ECN was specified as a modification to TCP's AIMD response: a marked packet triggers the same window reduction as a loss, but without dropping the packet. The ECN work assumed and reused the AIMD control law as the sender's reaction.
Carried by Sally Floyd; K. K. Ramakrishnan; RFC 2481 (1999).
Datagram and real-time media congestion control influenced by Additive increase/multiplicative decrease
DCCP's congestion-controlled datagram service offered pluggable algorithms, and its TCP-like profile reused AIMD window control for unreliable datagram traffic. The framework carried AIMD beyond TCP to applications that could not use TCP itself.
Carried by Eddie Kohler; Mark Handley; Sally Floyd.
Wireless and lossy-link congestion control influenced by Additive increase/multiplicative decrease
TCP Westwood kept AIMD's window-based control but replaced blind halving on loss with a window set from an estimate of the bottleneck rate. It took the AIMD framework and modified its loss response for lossy links.
Carried by TCP Westwood (2001).
Explicit Rate-Based Congestion Control reacted against Additive increase/multiplicative decrease
Explicit rate-based designs such as RCP were proposed as a replacement for AIMD's probing: routers would compute and stamp a fair rate so senders need not infer capacity from loss. They defined themselves against the slow convergence and queue buildup of AIMD.
Carried by Rate Control Protocol (RCP).
Explicit congestion signaling influenced by Active queue management
ECN generalized the AQM idea of an early, explicit router signal: instead of RED's probabilistic drop, a router sets a congestion bit. The ECN specification built directly on RED's threshold-based marking of incipient congestion.
Carried by Sally Floyd; K. K. Ramakrishnan.
Low-latency data-center congestion control influenced by Active queue management
Data-center congestion control revived active queue management in switches, using fine-grained queue and delay signals (including ECN marking) to keep latency low. The AQM premise that routers should signal early rather than let buffers fill carried into these designs.
Carried by DCTCP (2010).
Model-based bandwidth and delay estimation influenced by Delay-based congestion control
BBR's model of the path uses the minimum round-trip time as the propagation delay with empty queues, the same delay-based signal that Vegas had used to detect queue buildup. Model-based estimation generalized delay measurement into an explicit path model.
Carried by Neal Cardwell; TCP BBR (2016).
Explicit Rate-Based Congestion Control grew out of Explicit congestion signaling
Explicit rate control extended the explicit-signaling idea from a single congestion bit to a full rate value computed by routers. RCP and ATM ABR both grew out of the notion that the network should tell the sender directly rather than make it infer.
Carried by Rate Control Protocol (RCP).
Beyond the field
Where Congestion Control's ideas came from in other fields, and what they led to there.
Delay-based congestion control influenced Low-latency transport in Network Protocols
Low-latency transport drew on delay-based congestion control, notably the Vegas and FAST approaches that use queuing delay as a signal. Modern low-latency protocols refined delay-based congestion signalling for data-center and wide-area use.
Low-latency data-center congestion control influenced Low-latency transport in Network Protocols
Low-latency transport protocols such as those in modern data centers built on data-center congestion-control work, including DCTCP and its successors. The low-latency designs refined the congestion-control algorithms developed for data-center fabrics.
Datagram and real-time media congestion control influenced Low-latency transport in Network Protocols
Low-latency transport inherited congestion-control ideas from datagram and real-time media protocols such as RTP/RTCP and TFRC. The real-time media tradition supplied loss-tolerant, delay-sensitive congestion-control methods that low-latency transports adapted.
Wireless and lossy-link congestion control influenced Low-latency transport in Network Protocols
Low-latency transport borrowed from wireless and lossy-link congestion control, which had developed techniques for distinguishing congestion loss from random loss. Those techniques informed the design of low-latency protocols operating over varied links.
Explicit Rate-Based Congestion Control influenced by Congestion Pricing and Marginal-Cost Road Pricing in Transportation Economics
Explicit-rate congestion control schemes such as Kelly's rate-control formulation and the ATM ABR explicit-rate work drew directly on congestion-pricing and marginal-cost arguments: users' rates are set by shadow prices that reflect marginal cost of congestion at bottleneck links. This price-based decomposition of network utility maximisation is the conceptual core of explicit rate-based control.
Carried by Frank Kelly.
Low-latency data-center congestion control influenced by Software-Defined Networking in Networks
Software-defined networking gave data-center congestion control programmable switches and centralized visibility, which schemes such as centralized rate allocation and in-network telemetry rely on. The SDN architecture is a direct enabler of the approach.
Low-latency data-center congestion control influenced by Control-Data Plane Separation in Software Defined Networking
Data-center congestion control exploits control-data plane separation, using centralized or logically centralized controllers and switch telemetry to set rates and thresholds. The separation made fine-grained, network-wide rate coordination feasible.
Model-based bandwidth and delay estimation influenced by Queueing Theory in Stochastic Modeling
Model-based bandwidth and delay estimation fits queueing models to measured one-way delay, using the relationship between bottleneck queueing delay and sending rate to infer capacity. Queueing theory supplies the delay-versus-load model the estimators invert.
Delay-based congestion control influenced DDoS mitigation in Network Security
Congestion-control research on delay- and rate-based response to overload informed DDoS mitigation's traffic-shaping and rate-limiting responses to flood attacks.
Model-based bandwidth and delay estimation influenced by Networked and distributed control in Control Theory
Model-based estimators are embedded in distributed control loops across endpoints, and designers drew on networked control theory for stability and delay analysis. The transfer is methodological.

Congestion Control is a planet in Nousfarer
Its city has a tower for each of these 9 frameworks. Land, walk in, and climb one concept at a time.
Land on Congestion ControlRelated fields
Fields its ideas are linked to
- Network Protocols 4 links
- Control Theory 1 link
- Stochastic Modeling 1 link
- Networks 1 link
- Software Defined Networking 1 link
- Network Security 1 link
- Transportation Economics 1 link
More in Networks
- Network Architecture
- Network Protocols
- Networks
- Peer To Peer And Content Delivery
- Routing And Internetworking
- Software Defined Networking
- Wireless Networks
See where Congestion Control sits on the Map of Human Knowledge